© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8323
    Prev
    Next
    INDEX
    Explanations

    When Harry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IDENT
    0.40
     Daughters
    0.39
    㣩
    0.39
    omorf
    0.39
    ongan
    0.39
     IMM
    0.39
    ρυθ
    0.39
    astas
    0.37
     (++
    0.37
    ☦
    0.37
    POSITIVE LOGITS
    erb
    0.36
    विल
    0.35
     inability
    0.33
     एक्चुअली
    0.33
     концу
    0.33
    four
    0.33
     committees
    0.33
    로운
    0.32
    currently
    0.32
     Accessibility
    0.32
    Activations Density 0.001%

    No Known Activations